</>MCP Agents Market
Plugin

funNLP

by fighting41love82.5kPythonUpdated 2024-05-10

funNLP is a comprehensive Chinese natural language Plugin for Claude code

funNLP is a comprehensive Chinese natural language processing resource repository that aggregates dictionaries, corpora, toolkits, and pretrained models for over 100 NLP tasks. It provides ready-to-use datasets including sensitive word lists, named entity dictionaries (names, locations, companies), emotion lexicons, domain-specific vocabularies (medical, legal, financial, automotive), chat corpora, and Chinese word vectors. This collection serves as a one-stop resource hub for developers building Chinese NLP applications, offering both data assets and reference implementations.

Key Features

Sensitive word filtering databases for Chinese and English with specialized lists (profanity, political, terrorism-related terms)
Comprehensive name dictionaries including Chinese (modern/ancient), Japanese, and inference tools for gender from names
Phone number, email, and ID card extraction with carrier and location lookup for Chinese mobile numbers
Domain-specific vocabularies across 68 fields including IT, finance, medicine, law, automotive, and more (9.16M terms total)
Large-scale corpora: Chinese chat dialogues, rumor datasets, Baidu Q&A data, ancient poetry, and couplet datasets (700K+ pairs)
Pre-trained language models and Chinese word embeddings for various NLP tasks
Text processing utilities: simplified/traditional Chinese conversion, English-to-Chinese phonetic simulation, continuous English segmentation
Synonym, antonym, negation word libraries and sentiment value lexicons for opinion mining

Use Cases

  • 01Building content moderation systems with multi-language sensitive word filtering
  • 02Extracting structured information (names, phones, addresses, emails) from unstructured Chinese text
  • 03Training domain-specific NLP models using specialized vocabularies for healthcare, legal, or financial applications
  • 04Developing chatbots with access to large Chinese conversational corpora and pre-trained models
  • 05Creating text generation systems for Chinese poetry, couplets, or domain-specific content
  • 06Performing sentiment analysis on Chinese text using emotion lexicons and pre-built datasets

funNLP — FAQ

What is funNLP?+

funNLP is an open-source repository aggregating Chinese NLP resources including dictionaries, corpora, word vectors, and datasets for over 100 tasks such as named entity recognition, sentiment analysis, text classification, and information extraction.

How do I use funNLP resources?+

Clone the GitHub repository to access datasets and dictionaries directly. Resources are provided as data files (text, JSON, CSV) that can be integrated into your Python NLP projects or used with frameworks like BERT, GPT, and other language models.

Is funNLP free to use?+

Yes, funNLP is completely free and open-source. All resources are publicly available on GitHub for research and commercial use, though individual datasets may have their own licenses.

What prerequisites are needed?+

No API keys required. Basic Python knowledge is helpful for integrating the datasets. Some advanced features may require NLP libraries like jieba, HanLP, or deep learning frameworks (TensorFlow, PyTorch) depending on your use case.

Which AI clients or frameworks work with funNLP?+

funNLP provides raw data and resources compatible with any NLP framework or LLM including BERT, ChatGLM, LLaMA, GPT models, and Chinese-specific tools. It's framework-agnostic and serves as a data source rather than a specific client integration.

Does funNLP support languages other than Chinese?+

While primarily focused on Chinese NLP, funNLP includes some bilingual resources (Chinese-English sensitive words, multi-language name databases) and cross-lingual tools like phone number attribution and simplified/traditional Chinese conversion.

How do I install funNLP?+

Open the source repository on GitHub and follow its README. funNLP is a plugin — MCP Agents Market links you directly to the official repo.

Is funNLP free?+

funNLP is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches